© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26083
    Prev
    Next
    INDEX
    Explanations

    references to fairness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    458
    +0.14
    0.8%
    443
    +0.12
    0.7%
    246
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.14
    0.02
    503
    +0.12
    0.02
    443
    +0.11
    0.02
    Negative Logits
    peptide
    -1.66
    obar
    -1.52
    |_{
    -1.51
    ocytes
    -1.50
    ocyte
    -1.48
    ordinate
    -1.47
     appendix
    -1.41
    ÃŁ
    -1.38
    |_{\
    -1.35
    anov
    -1.35
    POSITIVE LOGITS
    grounds
    2.37
    yt
    2.28
    cloth
    2.21
    fax
    2.17
    ways
    1.98
    banks
    1.96
    ies
    1.95
    casters
    1.88
    leigh
    1.84
    yland
    1.84
    Activations Density 0.143%

    No Known Activations